GSCL : Generative Self-Supervised Contrastive Learning for Vein-Based Biometric Verification
Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
Original language | English |
---|---|
Pages (from-to) | 230-244 |
Journal / Publication | IEEE Transactions on Biometrics, Behavior, and Identity Science |
Volume | 6 |
Issue number | 2 |
Online published | 8 Feb 2024 |
Publication status | Published - Apr 2024 |
Link(s)
Abstract
Vein-based biometric technology offers secure identity authentication due to the concealed nature of blood vessels. Despite the promising performance of deep learning-based biometric vein recognition, the scarcity of vein data hinders the discriminative power of deep features, thus affecting overall performance. To tackle this problem, this paper presents a generative self-supervised contrastive learning (GSCL) scheme, designed from a data-centric viewpoint to fully mine the potential prior knowledge from limited vein data for improving feature representations. GSCL first utilizes a style-based generator to model vein image distribution and then generate numerous vein image samples. These generated vein images are then leveraged to pretrain the feature extraction network via self-supervised contrastive learning. Subsequently, the network undergoes further fine-tuning using the original training data in a supervised manner. This systematic combination of generative and discriminative modeling allows the network to comprehensively excavate the semantic prior knowledge inherent in vein data, ultimately improving the quality of feature representations. In addition, we investigate a multi-template enrollment method for improving practical verification accuracy. Extensive experiments conducted on public finger vein and palm vein databases, as well as a newly collected finger vein video database, demonstrate the effectiveness of GSCL in improving representation quality. © 2024 IEEE.
Research Area(s)
- Biometric vein verification, enrollment, generative adversarial network (GAN), representation learning, self-supervised contrastive learning (SCL)
Citation Format(s)
GSCL: Generative Self-Supervised Contrastive Learning for Vein-Based Biometric Verification. / Ou, Wei-Feng; Po, Lai-Man; Huang, Xiu-Feng et al.
In: IEEE Transactions on Biometrics, Behavior, and Identity Science, Vol. 6, No. 2, 04.2024, p. 230-244.
In: IEEE Transactions on Biometrics, Behavior, and Identity Science, Vol. 6, No. 2, 04.2024, p. 230-244.
Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review